摘要： 针对视频中的叠化与淡入淡出现象，提出一种基于三步筛选的渐变镜头检测算法。提取视频帧的亮度和方差作为特征，通过有限状态机实现初始渐变检测，并计算视频帧的颜色、共生矩阵、运动特征，从而进行三步筛选，保证检测的准确性。对TRECVID视频进行实验，结果表明，该算法对渐变具有较好的检测性能，对运动及闪光现象有较强的鲁棒性。

关键词: 镜头检测, 共生矩阵, 视频帧, 运动特征, 渐变

Abstract: Aiming at the dissolve and fade in fade out phenomenon of video, this paper proposes a video shot detection algorithm based on three steps filter. A finite state machine is used to search gradual transition candidates in intensity variance continuity signal, and verify those to get real gradual transitions, next, extract color, texture and motion feature of video frame to guarantee the precision of gradual shot detection. Experimental results based on the videos from TRECVID demonstrate good performance of the algorithm and its robustness against disturbances caused by object motion or flashlight.

Key words: shot detection, co-occurrence matrix, video frame, motion feature, gradual transition

中图分类号: 

• TP391